Multi-Horizon Demand Forecasting & Inventory Planning
What this system is for
A forecasting system that compares baselines and machine-learning models across multiple planning horizons.
Reference economics
€2.0M inventory → 5% less excess → €100k released.
Reference arithmetic, not a measured client result.
€2.0M
Inventory base
5%
Excess reduction
€100k
Capital released
The success story in 30 seconds
Business problem
Aggregate accuracy can hide weak planning performance and lead to the wrong stock, capacity or financial action.
What changed
Benchmark against simple statistical baselines.
Business utility
The useful output is not the prediction itself; it is a better decision made with explicit uncertainty.
Decision
Forecasting & planning
System
Multi-Horizon Demand Forecasting & Inventory Planning
Validation
WAPE · Bias
Core stack
Python · Statsmodels · Machine Learning